{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:32Z","timestamp":1784268392200,"version":"3.55.0"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-23-1-2641"],"award-info":[{"award-number":["N00014-23-1-2641"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01781","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19163-19173","source":"Crossref","is-referenced-by-count":3,"title":["Videoauteur: Towards Long Narrative Video Generation"],"prefix":"10.1109","author":[{"given":"Junfei","family":"Xiao","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Cheng","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Qi","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangke","family":"Gui","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanchuan","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiepeng","family":"Cen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibei","family":"Ma","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1086\/448619"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref5","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_27"},{"key":"ref9","article-title":"Dreamllm: Synergistic multimodal comprehension and creation","author":"Dong","year":"2023","journal-title":"arXiv"},{"key":"ref10","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Esser"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref12","article-title":"Datacomp: In search of the next generation of multimodal datasets","author":"Gadre","year":"2024","journal-title":"NeurlPS"},{"key":"ref13","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_37"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.12987\/9780300268461-084"},{"key":"ref16","article-title":"Animate-a-story: Storytelling with retrieval-augmented video generation","author":"He","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref18","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv"},{"key":"ref20","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurlPS"},{"key":"ref21","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv"},{"key":"ref22","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3398538"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref25","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2024","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref27","volume-title":"Flux","year":"2024"},{"key":"ref28","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref30","article-title":"Videodirectorgpt: Consistent multi-scene video generation via 11m-guided planning","author":"Lin","year":"2024","journal-title":"COLM"},{"key":"ref31","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurlPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.543"},{"key":"ref33","first-page":"2630","article-title":"Howto 100 m: Learning a text-video embedding by watching hundred million narrated video clips","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Miech"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref35","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00603"},{"key":"ref37","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurlPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_1"},{"key":"ref41","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv"},{"key":"ref42","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv"},{"key":"ref43","article-title":"Emu: Generative pretraining in multimodality","author":"Sun","year":"2023","journal-title":"ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref45","article-title":"Mm-interleaved: Interleaved image-text generative modeling via multi-modal feature synchronizer","author":"Tian","year":"2024","journal-title":"arXiv"},{"key":"ref46","article-title":"Videotetris: Towards compositional text-to-video generation","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv"},{"key":"ref50","article-title":"Semflow: Binding semantic segmentation and image synthesis via rectified flow","author":"Wang","year":"2024","journal-title":"NeurlPS"},{"key":"ref51","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref52","article-title":"Visionllm: Large language model is also an openended decoder for vision-centric tasks","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref55","article-title":"Seed-story: Multimodal long story generation with large language model","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00197"},{"key":"ref57","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00949"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.30"},{"key":"ref60","volume-title":"Llavanext: A strong zero-shot video understanding model","author":"Zhang","year":"2024"},{"key":"ref61","article-title":"Moviedreamer: Hierarchical generation for coherent long visual sequence","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref64","article-title":"Storydiffusion: Consistent selfattention for long-range image and video generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00841"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444035.pdf?arnumber=11444035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:50Z","timestamp":1777613330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01781","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}